Maxime Chevalier-Boisvert e1a6afbf81 Added code to train from one hot encoding %!s(int64=5) %!d(string=hai) anos
..
envs 97bca6e172 Fixed issues with dynamic obstacles env %!s(int64=5) %!d(string=hai) anos
__init__.py e7e870ce2d Fixed issues with wrappers %!s(int64=6) %!d(string=hai) anos
minigrid.py 9c57465a0a Implemented one-hot observation wrapper %!s(int64=5) %!d(string=hai) anos
register.py 5d9e8cab8a Fixed issue with default reward_threshold %!s(int64=5) %!d(string=hai) anos
rendering.py 6e77fbef44 Fixup %!s(int64=5) %!d(string=hai) anos
roomgrid.py 13d4651e03 Refactored to eliminate start_pos, simplify code. %!s(int64=5) %!d(string=hai) anos
wrappers.py e1a6afbf81 Added code to train from one hot encoding %!s(int64=5) %!d(string=hai) anos